Sample Metadata

metadata_legend <- data.table::fread('../data/metadata/metadata_legend.csv')

2018

metadata_2018 <- data.table::fread('../data/metadata/2018.csv')
metadata_2018[, Risk := "No"]
data.table::set(metadata_2018, which(metadata_2018$Microcystin > 1), "Risk", "Low")
data.table::set(metadata_2018, which(metadata_2018$Microcystin >= 10), "Risk", "Moderate")
data.table::set(metadata_2018, which(metadata_2018$Microcystin >= 50), "Risk", "High")

Download

2019

metadata_2019 <- data.table::fread('../data/metadata/2019.csv')
metadata_2019[, Risk := "No"]
data.table::set(metadata_2019, which(metadata_2019$Microcystin > 1), "Risk", "Low")
data.table::set(metadata_2019, which(metadata_2019$Microcystin >= 10), "Risk", "Moderate")
data.table::set(metadata_2019, which(metadata_2019$Microcystin >= 50), "Risk", "High")

Download

2020

metadata_2020 <- data.table::fread('../data/metadata/2020.csv')
metadata_2020[, Risk := "No"]
data.table::set(metadata_2020, which(metadata_2020$Microcystin > 1), "Risk", "Low")
data.table::set(metadata_2020, which(metadata_2020$Microcystin >= 10), "Risk", "Moderate")
data.table::set(metadata_2020, which(metadata_2020$Microcystin >= 50), "Risk", "High")

Download

Read Counts

ASV Table

read_counts <- construct_ASVtable('../data/16S_processing/finalized_reads')
read_counts <- read_counts[, c(TRUE, colSums(read_counts[,-1]) > 5000), with = FALSE]
data.table::setnames(read_counts, colnames(read_counts), gsub('_S.*', '', colnames(read_counts)))

Download

Classifications

classifications <- read_counts[[1]]
classifications <- dada2::assignTaxonomy(classifications, '../data/16S_processing/databases/rdp_train_set_18.fa.gz')
classifications <- dada2::assignTaxonomy(classifications, '../data/16S_processing/databases/silva_nr99_v138.1_train_set.fa.gz')

Download

Cyanobacteria

cyanobacteria <- classifications[Class == "Cyanobacteria"]
cyanobacteria <- dada2::assignSpecies(cyanobacteria[[1]], '../data/16S_processing/databases/rdp_species_assignment_18.fa.gz')

Phyloseq Object

lake_po <- phyloseq::phyloseq(phyloseq::otu_table(as.matrix(read_counts[,-1]), TRUE),
                              phyloseq::tax_table(as.matrix(classifications)),
                              phyloseq::sample_data(data.frame(rbind(
                                metadata_2018,
                                metadata_2019),
                                row.names = 1)))

Download



Schuyler Smith
Ph.D. Student - Bioinformatics and Computational Biology
Iowa State University. Ames, IA.